Provides situational awareness and identifies the next steps for a project by checking the workflow catalog.

Install

mkdir -p .claude/skills/help-hoatv2211 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10767" && unzip -o skill.zip -d .claude/skills/help-hoatv2211 && rm skill.zip

Installs to .claude/skills/help-hoatv2211

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Contextual assistance when the user is blocked or unsure what to do next.
73 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Identify current project phase from artifacts
  • Read session state to determine progress
  • Check step completion against workflow catalog
  • Identify blockers and next required steps
  • Perform formal readiness checks for phase transitions

How it works

The skill reads the workflow catalog and repository artifacts to determine the current project phase. It then compares completed work against required steps to identify blockers and suggest the next action.

Inputs & outputs

You give it
Current repository state and session history
You get back
Actionable next steps and phase status

When to use help

  • Determine project stage
  • Find out what to do next
  • Get status of current workflow

About this skill

Studio Help -- What Do I Do Next?

This skill is read-only. It reports findings but writes no files.

This skill figures out where the project is in the workflow and tells the user what comes next. It is lightweight -- not a full audit. For a full gap analysis, use /project-stage-detect after that skill is migrated.


Step 1: Read the Catalog

Read .github/docs/workflow-catalog.yaml. This is the authoritative list of phases, their ordered steps, whether each step is required or optional, and the artifact globs that indicate completion.


Step 2: Determine Current Phase

Check in this order:

  1. Read production/stage.txt. If it exists and has content, treat it as the authoritative stage name.
  2. If production/stage.txt is missing, infer phase from artifacts, using the most advanced match:
    • src/ has 10 or more source files -> production
    • files exist in production/epics/ or production/sprints/ -> pre-production
    • docs/architecture/adr-*.md exists -> technical-setup
    • design/gdd/systems-index.md exists -> systems-design
    • design/gdd/game-concept.md exists -> concept
    • otherwise -> concept

Step 3: Read Session Context

Read production/session-state/active.md if it exists. Extract:

  • what was most recently worked on,
  • any in-progress tasks or open questions,
  • current epic, feature, or task from a STATUS block if present.

Use this to personalize the answer.


Step 4: Check Step Completion for the Current Phase

For each step in the current phase from the catalog:

Artifact-based checks

If the step has artifact.glob:

  • use Glob to check whether matching files exist,
  • respect min_count if present,
  • if artifact.pattern exists, use Grep to confirm the pattern in the matched file,
  • mark the step complete only when the artifact condition is satisfied.

If the step has artifact.note and no glob:

  • mark it MANUAL -- cannot be auto-detected.

If the step has no artifact:

  • mark it UNKNOWN -- trackable only by user confirmation or session context.

Special case: repeatable steps

For repeatable steps, artifact detection shows that some work exists, not that the step is globally finished. Phrase results accordingly.


Step 5: Find Position and Identify Next Steps

Determine:

  • the last confirmed complete required step,
  • the first incomplete required step as the current blocker,
  • any optional steps available now,
  • the next required steps after the blocker.

If the user provided an argument such as finished design-review, use it to disambiguate an otherwise ambiguous position.


Step 6: Present Output

Keep the answer short and direct.

Use this structure:

## Where You Are: [Phase Label]

**In progress:** [from active.md, if any]

### Done
- [completed step]

### Next up (REQUIRED)
**[step name]** -- [description]
Command: `/command`

### Also available (OPTIONAL)
- **[step name]** -- [description] -> `/command`

### Coming up after that
- [next required step] (`/command`)

Formatting rules:

  • one primary recommendation only,
  • optional items are secondary,
  • if a step is MANUAL, ask the user whether it has been completed,
  • never auto-run the next skill.

If the user sounds lost or explicitly asks for more help, add these escalation paths:

  • /project-stage-detect -- full gap analysis
  • /gate-check -- formal readiness check for the next phase
  • /start -- re-orient from scratch

Verdict: COMPLETE


Collaborative Protocol

  • Never auto-run the next skill.
  • Ask about manual steps instead of assuming.
  • Match the user's tone.
  • Leave the user with one clear next action.

Required artifacts:

  • .github/docs/technical-preferences.md is populated
  • docs/architecture/architecture.md exists
  • at least 3 ADRs exist in docs/architecture/
  • docs/architecture/control-manifest.md exists
  • design/accessibility-requirements.md exists

Quality checks:

  • architecture covers core systems
  • technical preferences define conventions and budgets
  • no unresolved foundation-layer architectural blockers remain

Pre-Production -> Production

Required artifacts:

  • at least one sprint plan exists
  • epics and stories exist in production/epics/
  • key UX specs exist in design/ux/
  • core architecture and control manifest exist

Recommended but non-blocking:

  • a vertical slice exists and has been played
  • a vertical slice playtest report exists

Quality checks:

  • core loop has been validated as fun or intentionally accepted without a slice
  • core fantasy is represented in available playtest evidence
  • accepted ADRs exist for foundation/core systems

Production -> Polish

Required artifacts:

  • active code exists in src/
  • core mechanics are implemented end-to-end
  • tests exist for logic and integration coverage
  • at least one smoke-check result exists
  • at least 3 playtest sessions are documented

Quality checks:

  • tests pass
  • no critical known blockers remain
  • core loop matches design intent
  • performance is within budget or explicit concerns are recorded

Polish -> Release

Required artifacts:

  • release checklist exists or has been completed
  • changelog or patch notes draft exists
  • QA sign-off artifact exists
  • localization and content-complete evidence exists where applicable

Quality checks:

  • no critical, high, or medium-severity release blockers remain
  • performance targets are met on target platforms
  • packaging and release pipeline are validated

3. Run the Gate

For the selected transition:

  • inspect each required artifact,
  • evaluate quality checks using available docs,
  • note missing items as blockers,
  • note recommended-but-missing items as concerns.

If review mode is full or lean, spawn the relevant phase gates in parallel:

  • creative-director -> CD-PHASE-GATE
  • technical-director -> TD-PHASE-GATE
  • producer -> PR-PHASE-GATE
  • art-director -> AD-PHASE-GATE when visual direction is relevant

If review mode is solo, skip director gates and note that the result is based only on artifact and document checks.

Apply the strictest verdict when multiple gate reviewers disagree.


4. Output Format

Return the result in this form:

## Gate Check: [Current] -> [Target]

### Required Artifacts
- [item] -- PASS / FAIL

### Quality Checks
- [item] -- PASS / CONCERNS / FAIL

### Director Reviews
- [gate] -- READY / CONCERNS / NOT READY

### Blockers
1. [blocking issue]

### Concerns
1. [non-blocking issue]

### Verdict: [PASS / CONCERNS / FAIL]

Verdict rules:

  • PASS: all required items satisfied, no blocking issues
  • CONCERNS: non-blocking gaps remain, but advancement is still defensible
  • FAIL: one or more required artifacts or quality gates are missing or not ready

5. Advancement Handling

If the verdict is PASS, ask the user whether to advance the stage. If yes:

  • write the new stage name to production/stage.txt
  • confirm that the stage file was updated

If the verdict is CONCERNS, ask whether the user wants to:

  • revise blockers now,
  • accept the risk and proceed,
  • stop and review later.

If the verdict is FAIL, do not advance the stage. Provide the single most important next fix first.

Verdict: COMPLETE

When not to use it

  • When a full gap analysis is required instead of lightweight assistance
  • When the user wants to auto-run the next skill

Prerequisites

.github/docs/workflow-catalog.yamlproduction/stage.txt

Limitations

  • Cannot auto-detect steps without defined artifact globs
  • Read-only; does not write files or run subsequent skills

How it compares

It provides a lightweight, read-only status check compared to manual auditing or full gap analysis tools.

Compared to similar skills

help side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
help (this skill)02moNo flagsBeginner
notion-meeting-intelligence66moNo flagsIntermediate
resume-handoff36moNo flagsIntermediate
meeting-briefing26moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

notion-meeting-intelligence

openai

Prepare meeting materials with Notion context and Codex research; use when gathering context, drafting agendas/pre-reads, and tailoring materials to attendees.

656

resume-handoff

parcadei

Resume work from handoff document with context analysis and validation

333

meeting-briefing

anthropics

Prepare structured briefings for meetings with legal relevance and track resulting action items. Use when preparing for contract negotiations, board meetings, compliance reviews, or any meeting where legal context, background research, or action tracking is needed.

213

personal-assistant

ailabs-393

This skill should be used whenever users request personal assistance tasks such as schedule management, task tracking, reminder setting, habit monitoring, productivity advice, time management, or any query requiring personalized responses based on user preferences and context. On first use, collects comprehensive user information including schedule, working habits, preferences, goals, and routines. Maintains an intelligent database that automatically organizes and prioritizes information, keeping relevant data and discarding outdated context.

36

digital-brain

muratcankoylan

This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content creation, network management, or voice consistency.

15

meeting-sync

amanaiproduct

Sync new Granola meetings to local Knowledge folder. Use during morning planning, when user asks "what should I do today", or asks to review/sync meetings.

13

Search skills

Search the agent skills registry